Information Gain-Guided Causal Intervention for Autonomous Debiasing Large Language Models
Despite significant progress, recent studies indicate that current large language models (LLMs) may still capture dataset biases and utilize them during inference, leading to the poor generalizability of LLMs. However, due to the diversity of dataset biases and the insufficient nature of bias suppression based on in-context learning, the effectiveness of previous prior knowledge-based debiasing methods and in-context learning based automatic debiasing methods is limited. To address these challenges, we explore the combination of causal mechanisms with information theory and propose an information gain-guided causal intervention debiasing (IGCIDB) framework. This framework first utilizes an information gain-guided causal intervention method to automatically and autonomously balance the distribution of instruction-tuning dataset. Subsequently, it employs a standard supervised fine-tuning process to train LLMs on the debiased dataset. Experimental results show that IGCIDB can effectively debias LLM to improve its generalizability across different tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityIn-Context LearningSimilar Papers 제목 키워드 기반
A Generalizable Physics-guided Causal Model for Trajectory Prediction in Autonomous Driving
Trajectory prediction for traffic agents is critical for safe autonomous driving. However, achieving effective zero-shot generalization in previously unseen domains remains a significant challenge. Motivated by the consi…
Zero-shot GeneralizationTrajectory PredictionAutonomous DrivingCRRL: A Causality-Based Reinforcement Learning Framework for Autonomous System Recovery
Traditional reinforcement learning (RL) for recovery in autonomous systems lacks causal understanding and generalizes poorly to novel failure scenarios. RL policies often stall in failure states, spending up to 70% of an…
Reinforcement LearningProbability trees and the value of a single intervention
The most fundamental problem in statistical causality is determining causal relationships from limited data. Probability trees, which combine prior causal structures with Bayesian updates, have been suggested as a possib…
Active LearningActive Causal Experimentalist (ACE): Learning Intervention Strategies via Direct Preference Optimization
Discovering causal relationships requires controlled experiments, but experimentalists face a sequential decision problem: each intervention reveals information that should inform what to try next. Traditional approaches…
Domain AdaptationActive learning of causal probability trees
The past two decades have seen a growing interest in combining causal information, commonly represented using causal graphs, with machine learning models. Probability trees provide a simple yet powerful alternative repre…
Active Learning